The National Robotics Engineering Center is looking for a Machine Learning Engineer to develop machine learning algorithms and applications for …

Quanergy Systems, Inc., a leading provider of OPA-based solid state LiDAR sensors and smart 3D solutions for automotive and IoT, announced the release of QORTEX DTC 2.2, the latest version of its 3D perception software, designed for advanced smart city and security applications. In June, Quanergy entered into a definitive merger agreement with CITIC Capital Acquisition Corp. (NYSE: CCAC) ("CCAC"). Upon closing of the transaction, the combined company will be named Quanergy Systems, Inc. and is expected to be listed on the New York Stock Exchange (NYSE) under the ticker symbol "QNGY." The transaction is expected to close in the fourth quarter of 2021, subject to satisfaction of customary closing conditions. QORTEX DTC is a core proprietary computer vision software platform compatible with Quanergy's suite of LiDAR sensors.

Safety constraints are essential for reinforcement learning (RL) applied in real-world situations. Chance constraints are suitable to represent the safety requirements in stochastic systems. Most existing RL methods with chance constraints have a low convergence rate, and only learn a conservative policy. In this paper, we propose a model-based chance constrained actor-critic (CCAC) algorithm which can efficiently learn a safe and non-conservative policy. Different from existing methods that optimize a conservative lower bound, CCAC directly solves the original chance constrained problems, where the objective function and safe probability is simultaneously optimized with adaptive weights. In order to improve the convergence rate, CCAC utilizes the gradient of dynamic model to accelerate policy optimization. The effectiveness of CCAC is demonstrated by an aggressive car-following task. Experiments indicate that compared with previous methods, CCAC improves the performance by 57.6% while guaranteeing safety, with a five times faster convergence rate.

To increase the trustworthiness of deep neural network (DNN) classifiers, an accurate prediction confidence that represents the true likelihood of correctness is crucial. Towards this end, many post-hoc calibration methods have been proposed to leverage a lightweight model to map the target DNN's output layer into a calibrated confidence. Nonetheless, on an out-of-distribution (OOD) dataset in practice, the target DNN can often mis-classify samples with a high confidence, creating significant challenges for the existing calibration methods to produce an accurate confidence. In this paper, we propose a new post-hoc confidence calibration method, called CCAC (Confidence Calibration with an Auxiliary Class), for DNN classifiers on OOD datasets. The key novelty of CCAC is an auxiliary class in the calibration model which separates mis-classified samples from correctly classified ones, thus effectively mitigating the target DNN's being confidently wrong. We also propose a simplified version of CCAC to reduce free parameters and facilitate transfer to a new unseen dataset. Our experiments on different DNN models, datasets and applications show that CCAC can consistently outperform the prior post-hoc calibration methods.